INDEX
Model
gemma-2-9b-it
Layer #
20
Steering Hook
blocks.20.hook_resid_pre
Steering Strength
56.5
Uploader
bot-neuronpedia
Created At
2/15/2025 1:06:43 AM
Raw Vector
Actions
Explanations
punctuation marks and structural elements in text
New Auto-Interp
Negative Logits
recognised
-0.38
nawr
-0.35
recognise
-0.34
unrivalled
-0.33
)
-0.32
instancetype
-0.32
recognising
-0.31
aras
-0.31
cucharadita
-0.30
-0.30
POSITIVE LOGITS
ſelf
0.77
queſta
0.74
betweenstory
0.70
fromnode
0.63
Infórmanos
0.60
kasarigan
0.60
ंदीखरीदारी
0.59
ſelves
0.59
ſta
0.59
defaultstate
0.58
Activations Density 1.275%